TREC Legal Track Learning Task Final Guidelines (revision 0.0)
|
|
- Jewel McLaughlin
- 5 years ago
- Views:
Transcription
1 TREC Legal Track Learning Task Final Guidelines (revision 0.0) Gordon V. Cormack Maura R. Grossman Abstract In the learning task, participants are given a seed set of documents from a larger collection that have previously been assessed by TREC as responsive or non-responsive to a legal discovery request. Using this information, participants must (a) rank the documents in the larger collection from most likely to least likely to be responsive; and (b) for each document, estimate the likelihood of responsiveness as a probability. The ranking will be evaluated by how well it places responsive documents before non-responsive ones, as assessed by TREC. The likelihood estimate will be evaluated by how well it estimates recall throughout the ranked list. 1 e-discovery Context The learning task models the use of automatic or semi-automatic methods to guide review strategy for the first or later passes of a multi-stage document review effort, organized as follows: 1. Preliminary search and asessment. The responding party analyzes the production request. Using ad hoc methods the team identifies a seed set of potentially responsive documents, and assesses each as responsive or not. 2. Learning by example. A learning method is used to rank the documents in the collection from most to least likely to be responsive to the production request, and to estimate this likelihood for 1
2 1 e-discovery Context 2 each document. The input to the learning method consists of the seed set, the assessments for the seed set, and the unranked collection; the output is a ranked list consisting of the document identifer and a probability of responsiveness for each document in the collection. The two components of learning by example ranking and estimation may be accomplished by the same method or by different methods. Either may be automated or manual. For example, ranking may be done using an information retrieval method or by human review using a five-point scale. Estimation may be done in the course of ranking or, for example, by sampling and reviewing documents at representative ranks. 3. Review process. A review process may be conducted, with strategy guided by the ranked list. One possible strategy is to review documents in order, thus discovering as many responsive documents as possible for a given amount of effort. Another possible strategy is triage: to review only mid-ranked documents, deeming, without further review, the top-ranked ones to be responsive, and the bottom-ranked ones to be non-responsive. Review strategy may be guided not only by the order of the ranked list, as outlined above, but also by the estimated effectiveness of various alternatives. Consider the strategy of reviewing the topranked documents. Where should a cut be made so that documents above the cut are reviewed and documents below are not? For triage, where should the two necessary cuts be made? Practically every review strategy decision boils down to the question, Of this particular set of documents, how many are responsive and how many are not? An informed choice of where to make the cut demands that we know how many documents both above and below the cut are responsive. There is no single correct answer the best choice depends on the relative risks, costs and benefits of missing responsive documents or of reviewing or producing non-responsive documents. In discovery efforts,
3 2 TREC Context 3 the cost of failing to produce responsive documents is typically much higher than the cost of producing non-responsive ones (unless they are privileged!). The specific tradeoff will be different in almost every matter. For this reason, we require not that the learning method make the cut, but that it provide the necessary information to make the best cut for the particular situation. To this end, we require an estimate of the probability that any particular document is responsive. If the probability estimates are accurate, it follows that the number of responsive documents in any set will be the sum of the probabilities associated with the documents in the set. Suppose the cost of missing a responsive document is estimated to be $95 and the cost of reviewing a non-responsive one is $5. It therefore follows that the best strategy is to review whose documents whose probability of relevance is above 5%, and none below. One simply has to sum the estimates to find the cut that makes this tradeoff. When opposing counsel demands to know how many documents were missed, or why they weren t identified, the estimate yields a defensible answer. 2 TREC Context This task is part of the TREC 2010 Legal Track. TREC The Text Retrieval Conference has the following goals: to encourage research in information retrieval based on large test collections; to increase communication among industry, academia, and government by creating an open forum for the exchange of research ideas; to speed the transfer of technology from research labs into commercial products by demonstrating substantial improvements in retrieval methodologies on real-world problems; and to increase the availability of appropriate evaluation techniques for use by industry and academia, including development of new evaluation techniques more applicable to current systems.
4 3 Task Details 4 The Legal Track, in its 5th year, pursues these goals within the context of electronic discovery. The Learning task is a successor to the batch task of TREC The principal differences are in focus, the requirement to rank every document in the corpus, and the requirement to provide a likelihood estimate for every document in the corpus. In addition, the task uses the same collection and some of the same production requests as its sister task, the TREC 2010 Legal Interactive Task, to facilitate comparison. 3 Task Details There will be eight production requests, each using the Enron document collection. For each request, the participating team will be given the text of the request, guidelines for its interpretation, a seed set of documents, and assessments for the seed documents. The results for all eight requests must be encoded in a text file according to the standard TREC format, where each line contains: requestid Q0 docid rank estp runid requestid is a number assigned by TREC identifying the production request. Q0 is a historical artifact of the TREC format. docid is a TREC-assigned document identifier. rank is the ranking of the document by estp, where 1 is the most likely relevant document for the request. estp is a probability estimate between 0.0 and 1.0. runid is a unique identifier for the submission, formed by joining a sequence of 3 or 4 characters identifying the team (composed by participant) a sequence of 3 or 4 charecters identifying the method (composed by participant) Capital A if the method is fully automated; capital M if the method is fully manual, meaning the seed documents are not used as input to any program; capital T if both automated and manual methods are used.
5 4 Manner of participation 5 The task will use the EDRM Enron v2 collection, which may be downloaded without restriction from the Web. 1 in either EDRM XML or PST formats. The document ids will be those from the EDRM XML format. Mapping files will be provided to convert information derivable from the PST-format documents to document ids. For the learning task, a document is considered to be either an message as a whole, or a particular attachment to an message. The EDRM XML version contains both native and text versions of each document, each with a unique identifier. The PST version contains the complete messages; participants will need to extract the attachments from these messages and treat them as separate documents. The Enron corpus contains many duplicate documents. For efficiency, submissions should refer to only the canonical document from each set of duplicates, as defined by TREC. 2 A mapping is provided from all document identifiers to canonical documents, so participants may eliminate duplicates prior to processing, or after the fact. The EDRM download is approximately 100GB in size. As a convenience, TREC is providing to participants a download for the text version of all canonical documents as a separate download (609 MB). Furthermore, TREC is providing the native version of all canonical attachments (7 GB). 4 Manner of participation We hope to attract participants that use various combinations of manual effort and technology. It is possible and desirable that a participating team employ two or more of the strategies, provided that the efforts are organized to conform to the information flow constraints. That is, a group might complete a fully automated review, and then undertake a technology-assisted review; or, a group might complete a manual review, and then undertake a technology-assisted review. Or a group might undertake manual and automated reviews concurrently, provided no input to the automated system, including tuning, was done by any individual having seen the production request or associated materials
6 5 Evaluation Details 6 Teams are free and encouraged to participate also in the TREC 2010 Legal Interactive Task, which will have three production requests and a privilege review. 5 Evaluation Details The effectiveness of ranking will be evaluated separately from the effectiveness of estimation. Several measures will be computed for each. The principal measures being considered to evaluate ranking are: Receiver operating characteristic (ROC) curves to display the tradeoff between missed responsive documents and produced non-responsive documents (false negatives and false positives) for all posible cuts. Area under the ROC curve (AUC) to serve as a summary measure of ranking effectiveness. AUC can be interpreted in terms of a very simple game (see below). Precision and recall at specific cuts, such as 10, 1000, documents. R-Precision. Average Precision. For estimation the principal measures being considered are: Root-mean-squared Average Recall Error (RMSRE). The RMS difference between estimated recall and actual recall, at all recall levels. Information Gain (IG). An information-theoretic measure that captures both the accuracy of the estimates and the effectiveness of the ranking. IG can be interpreted in terms of a very simple game (see below). F1. The actual F1@K measure (used in other legal tasks) achieved when K is the cut value that optimizes apparent F1@K. Apparent F1. The value of F1@K, if the estimates were accurate.
7 6 The Information Gain Game 7 6 The Information Gain Game We illustrate the notion of information gain with a game. It is not necessary to understand the theory behind it, as the rules and strategy are simple. You are given a sequence of documents to review, in some arbitrary order; For each document, you must guess a number estp between 0 and 1, which is your estimate of the likelihood that the document is responsive. (It would be inadvisable to guess 0 or 1 exactly, as the downside of an incorrect guess would be infinite.) If the document turns out to be responsive, your score is IG = 1 + log 2 estp If the document turns out to be non-responsive your score is IG = 1 + log 2 (1 estp ) A strategy to play well has the following elements: If you think the document is responsive, choose estp > 1 2 If you are pretty confident the document is responsive, choose estp 1 2 Don t be overconfident. Never choose estp = 1. If you think the document is non-responsive, choose estp < 1 2 If you are pretty confident the document is non-responsive, choose estp 1 2 Don t be overconfident. Never choose estp = 0.
8 7 The AUC Game 8 The best possible score, on average, is achieved if estp is in fact an accurate estimate of the probability. If you think the document is responsive and you think there s a 65% chance you re right, guess estp = If your guesses are sensiblee, you ll get a positive average IG score. If you get a negative IG score, you would have been better off flipping a coin! 7 The AUC Game The AUC game works like this: You are given a stack of documents, that you arrange with the most likely to be responsive on top, and so on down to the least likely on the bottom. For every responsive document and for every non-responsive document in the stack, if the responsive document is above the nonresponsive one, you score a point; otherwise you score 0. Your AUC score is AUC = points R N were points is the total number of points you scored, R is the number of responsive documents, and N is the number of nonresponsive documents.
Overview of the TREC 2005 Spam Track. Gordon V. Cormack Thomas R. Lynam. 18 November 2005
Overview of the TREC 2005 Spam Track Gordon V. Cormack Thomas R. Lynam 18 November 2005 To answer questions! Why Standardized Evaluation? Is spam filtering a viable approach? What are the risks, costs,
More information1.2 Adding Integers. Contents: Numbers on the Number Lines Adding Signed Numbers on the Number Line
1.2 Adding Integers Contents: Numbers on the Number Lines Adding Signed Numbers on the Number Line Finding Sums Mentally The Commutative Property Finding Sums using And Patterns and Rules of Adding Signed
More informationA. Incorrect! This would be the negative of the range. B. Correct! The range is the maximum data value minus the minimum data value.
AP Statistics - Problem Drill 05: Measures of Variation No. 1 of 10 1. The range is calculated as. (A) The minimum data value minus the maximum data value. (B) The maximum data value minus the minimum
More informationTechnical Brief: Domain Risk Score Proactively uncover threats using DNS and data science
Technical Brief: Domain Risk Score Proactively uncover threats using DNS and data science 310 Million + Current Domain Names 11 Billion+ Historical Domain Profiles 5 Million+ New Domain Profiles Daily
More informationBulgarian Math Olympiads with a Challenge Twist
Bulgarian Math Olympiads with a Challenge Twist by Zvezdelina Stankova Berkeley Math Circle Beginners Group September 0, 03 Tasks throughout this session. Harder versions of problems from last time appear
More informationEXAM PREPARATION GUIDE
When Recognition Matters EXAM PREPARATION GUIDE PECB Certified ISO 14001 Lead Implementer www.pecb.com The objective of the PECB Certified ISO 14001 Lead Implementer examination is to ensure that the candidate
More informationHow to Jump-Start Early Case Assessment. A Case Study based on TREC 2008
How to Jump-Start Early Case Assessment A Case Study based on TREC 2008 For over a decade, the National Institute of Standards and Technology ( NIST ) has cosponsored the Text Retrieval Conference ( TREC
More informationSlice Intelligence!
Intern @ Slice Intelligence! Wei1an(Wu( September(8,(2014( Outline!! Details about the job!! Skills required and learned!! My thoughts regarding the internship! About the company!! Slice, which we call
More informationThreat and Vulnerability Assessment Tool
TABLE OF CONTENTS Threat & Vulnerability Assessment Process... 3 Purpose... 4 Components of a Threat & Vulnerability Assessment... 4 Administrative Safeguards... 4 Logical Safeguards... 4 Physical Safeguards...
More informationEXAM PREPARATION GUIDE
When Recognition Matters EXAM PREPARATION GUIDE PECB Certified ISO 22000 Lead Implementer www.pecb.com The objective of the Certified ISO 22000 Lead Implementer examination is to ensure that the candidate
More informationEXAM PREPARATION GUIDE
When Recognition Matters EXAM PREPARATION GUIDE PECB Certified ISO 31000 Risk Manager www.pecb.com The objective of the PECB Certified ISO 31000 Risk Manager examination is to ensure that the candidate
More informationLearning internal representations
CHAPTER 4 Learning internal representations Introduction In the previous chapter, you trained a single-layered perceptron on the problems AND and OR using the delta rule. This architecture was incapable
More informationEXAM PREPARATION GUIDE
When Recognition Matters EXAM PREPARATION GUIDE PECB Certified ISO/IEC 27005 Risk Manager www.pecb.com The objective of the PECB Certified ISO/IEC 27005 Risk Manager examination is to ensure that the candidate
More informationRank Measures for Ordering
Rank Measures for Ordering Jin Huang and Charles X. Ling Department of Computer Science The University of Western Ontario London, Ontario, Canada N6A 5B7 email: fjhuang33, clingg@csd.uwo.ca Abstract. Many
More informationInformation Retrieval
Information Retrieval ETH Zürich, Fall 2012 Thomas Hofmann LECTURE 6 EVALUATION 24.10.2012 Information Retrieval, ETHZ 2012 1 Today s Overview 1. User-Centric Evaluation 2. Evaluation via Relevance Assessment
More informationTRANSANA and Chapter 8 Retrieval
TRANSANA and Chapter 8 Retrieval Chapter 8 in Using Software for Qualitative Research focuses on retrieval a crucial aspect of qualitatively coding data. Yet there are many aspects of this which lead to
More informationLIS 2680: Database Design and Applications
School of Information Sciences - University of Pittsburgh LIS 2680: Database Design and Applications Summer 2012 Instructor: Zhen Yue School of Information Sciences, University of Pittsburgh E-mail: zhy18@pitt.edu
More informationCH 87 FUNCTIONS: TABLES AND MAPPINGS
CH 87 FUNCTIONS: TABLES AND MAPPINGS INTRODUCTION T he notion of a function is much more abstract than most of the algebra concepts you ve seen so far, so we ll start with three specific non-math examples.
More informationITG. Information Security Management System Manual
ITG Information Security Management System Manual This manual describes the ITG Information Security Management system and must be followed closely in order to ensure compliance with the ISO 27001:2005
More informationBPS Suite and the OCEG Capability Model. Mapping the OCEG Capability Model to the BPS Suite s product capability.
BPS Suite and the OCEG Capability Model Mapping the OCEG Capability Model to the BPS Suite s product capability. BPS Contents Introduction... 2 GRC activities... 2 BPS and the Capability Model for GRC...
More informationITG. Information Security Management System Manual
ITG Information Security Management System Manual This manual describes the ITG Information Security Management system and must be followed closely in order to ensure compliance with the ISO 27001:2005
More informationCATALOG 2017/2018 BINUS UNIVERSITY. Cyber Security. Introduction. Vision. Mission
Cyber Security Introduction Cyber attack is raising and threaten ubiquitous world on internet today. Industry and government need cyber security expert to counter and defend from this threaten. Cyber Security
More information[Maria Jackson Hittle] Thanks, Michael. Since the RSR was implemented in 2009, HAB has been slowing shifting its focus from data submission to data
[Michael Costa] Welcome to today s Webcast. Thank you so much for joining us today! My name is Michael Costa. I m a member of the DART Team, one of several groups engaged by HAB to provide training and
More informationLearning Objectives. Outline. Lung Cancer Workshop VIII 8/2/2012. Nicholas Petrick 1. Methodologies for Evaluation of Effects of CAD On Users
Methodologies for Evaluation of Effects of CAD On Users Nicholas Petrick Center for Devices and Radiological Health, U.S. Food and Drug Administration AAPM - Computer Aided Detection in Diagnostic Imaging
More informationTransactions Lab I. Tom Kelliher, CS 317
Transactions Lab I Tom Kelliher, CS 317 The purpose of this lab is for you to gain some understanding of how transactions work, see for yourselves how the various SQL isolation levels correspond to the
More informationHOLA: Human-like Orthogonal Network Layout
HOLA: Human-like Orthogonal Network Layout S. Kieffer, T. Dwyer, K. Marriot, and M. Wybrow Emily Hindalong CPSC 547 Presentation Novermber 17, 2015 1 In a Nutshell... Let s analyze human-drawn networks
More informationMeasuring Intrusion Detection Capability: An Information- Theoretic Approach
Measuring Intrusion Detection Capability: An Information- Theoretic Approach Guofei Gu, Prahlad Fogla, David Dagon, Wenke Lee Georgia Tech Boris Skoric Philips Research Lab Outline Motivation Problem Why
More informationISO 31000:2009 & COSO ERM
ISO 31000:2009 & COSO ERM Jakarta, 2018 Facilitators: Dr. Antonius Alijoyo MBA., ERMCP., CERG., CGAP., CCSA., CFSA., CGEIT., CFE - Ketua KomTek 03-10 BSN - Founder CRMS Indonesia - Ketua Umum IRMAPA COSO
More informationWye Valley NHS Trust. Data protection audit report. Executive summary June 2017
Wye Valley NHS Trust Data protection audit report Executive summary June 2017 1. Background The Information Commissioner is responsible for enforcing and promoting compliance with the Data Protection Act
More informationFoundation Level Syllabus Usability Tester Sample Exam
Foundation Level Syllabus Usability Tester Sample Exam Version 2017 Provided by German Testing Board Copyright Notice This document may be copied in its entirety, or extracts made, if the source is acknowledged.
More informationOverview of the INEX 2009 Link the Wiki Track
Overview of the INEX 2009 Link the Wiki Track Wei Che (Darren) Huang 1, Shlomo Geva 2 and Andrew Trotman 3 Faculty of Science and Technology, Queensland University of Technology, Brisbane, Australia 1,
More informationIntroduction to the American Academy of Forensic Sciences Standards Board
Introduction to the American Academy of Forensic Sciences Standards Board Introduction Teresa Ambrosius, Secretariat Mary McKiel, Communication Liaison Technical Coordinator Position to be filled Background
More information2. On classification and related tasks
2. On classification and related tasks In this part of the course we take a concise bird s-eye view of different central tasks and concepts involved in machine learning and classification particularly.
More informationThis chapter continues our overview of public-key cryptography systems (PKCSs), and begins with a description of one of the earliest and simplest
1 2 3 This chapter continues our overview of public-key cryptography systems (PKCSs), and begins with a description of one of the earliest and simplest PKCS, Diffie- Hellman key exchange. This first published
More informationEquating. Lecture #10 ICPSR Item Response Theory Workshop
Equating Lecture #10 ICPSR Item Response Theory Workshop Lecture #10: 1of 81 Lecture Overview Test Score Equating Using IRT How do we get the results from separate calibrations onto the same scale, so
More informationDefinition: A data structure is a way of organizing data in a computer so that it can be used efficiently.
The Science of Computing I Lesson 4: Introduction to Data Structures Living with Cyber Pillar: Data Structures The need for data structures The algorithms we design to solve problems rarely do so without
More informationUsing TAR 2.0 to Streamline Document Review for Japanese Patent Litigation
877.557.4273 catalystsecure.com CASE STUDY Using TAR 2.0 to Streamline Document Review for Japanese Patent Litigation Continuous Active Review Cuts Cost by Over 85% Catalyst s review platform and its ability
More informationWeek 7 Picturing Network. Vahe and Bethany
Week 7 Picturing Network Vahe and Bethany Freeman (2005) - Graphic Techniques for Exploring Social Network Data The two main goals of analyzing social network data are identification of cohesive groups
More informationCS261: A Second Course in Algorithms Lecture #14: Online Bipartite Matching
CS61: A Second Course in Algorithms Lecture #14: Online Bipartite Matching Tim Roughgarden February 18, 16 1 Online Bipartite Matching Our final lecture on online algorithms concerns the online bipartite
More informationALGORITHMIC TRADING AND ORDER ROUTING SERVICES POLICY
ALGORITHMIC TRADING AND ORDER ROUTING SERVICES POLICY Please respond to: Trading Operations THE LONDON METAL EXCHANGE 10 Finsbury Square, London EC2A 1AJ Tel +44 (0)20 7113 8888 Registered in England no
More informationEvaluation. David Kauchak cs160 Fall 2009 adapted from:
Evaluation David Kauchak cs160 Fall 2009 adapted from: http://www.stanford.edu/class/cs276/handouts/lecture8-evaluation.ppt Administrative How are things going? Slides Points Zipf s law IR Evaluation For
More informationVocabulary: Looking For Pythagoras
Vocabulary: Looking For Pythagoras Concept Finding areas of squares and other figures by subdividing or enclosing: These strategies for finding areas were developed in Covering and Surrounding. Students
More informationLab 2 Test collections
Lab 2 Test collections Information Retrieval, 2017 Goal Introduction The objective of this lab is for you to get acquainted with working with an IR test collection and Lemur Indri retrieval system. Instructions
More informationHi everyone. I hope everyone had a good Fourth of July. Today we're going to be covering graph search. Now, whenever we bring up graph algorithms, we
Hi everyone. I hope everyone had a good Fourth of July. Today we're going to be covering graph search. Now, whenever we bring up graph algorithms, we have to talk about the way in which we represent the
More informationQ: Can we download a copy of the ICM/FSA video presentation for reference?
General Q: Can we download a copy of the ICM/FSA video presentation for reference? A: Yes. A PowerPoint document is posted under the General Information section of the ICM Dashboard. Q: Is it OK not to
More informationp x i 1 i n x, y, z = 2 x 3 y 5 z
3 Pairing and encoding functions Our aim in this part of the course is to show that register machines can compute everything that can be computed, and to show that there are things that can t be computed.
More informationThe Basics of Graphical Models
The Basics of Graphical Models David M. Blei Columbia University September 30, 2016 1 Introduction (These notes follow Chapter 2 of An Introduction to Probabilistic Graphical Models by Michael Jordan.
More informationInformed Search CS457 David Kauchak Fall 2011
Admin Informed Search CS57 David Kauchak Fall 011 Some material used from : Sara Owsley Sood and others Q3 mean: 6. median: 7 Final projects proposals looked pretty good start working plan out exactly
More informationEnhancing the Cybersecurity of Federal Information and Assets through CSIP
TECH BRIEF How BeyondTrust Helps Government Agencies Address Privileged Access Management to Improve Security Contents Introduction... 2 Achieving CSIP Objectives... 2 Steps to improve protection... 3
More informationVariables and Data Representation
You will recall that a computer program is a set of instructions that tell a computer how to transform a given set of input into a specific output. Any program, procedural, event driven or object oriented
More informationEDRMS Document Migration Guideline
Title EDRMS Document Migration Guideline Creation Date 23 December 2016 Version 3.0 Last Revised 28 March 2018 Approved by Records Manager and IT&S Business Partner Approval date 28 March 2018 TABLE OF
More informationSynology Security Whitepaper
Synology Security Whitepaper 1 Table of Contents Introduction 3 Security Policy 4 DiskStation Manager Life Cycle Severity Ratings Standards Security Program 10 Product Security Incident Response Team Bounty
More informationEXAM PREPARATION GUIDE
When Recognition Matters EXAM PREPARATION GUIDE PECB Certified ISO/IEC 20000 Lead Auditor www.pecb.com The objective of the Certified ISO/IEC 20000 Lead Auditor examination is to ensure that the candidate
More informationCSCI 5417 Information Retrieval Systems. Jim Martin!
CSCI 5417 Information Retrieval Systems Jim Martin! Lecture 7 9/13/2011 Today Review Efficient scoring schemes Approximate scoring Evaluating IR systems 1 Normal Cosine Scoring Speedups... Compute the
More informationSandeep Kharidhi and WenSui Liu ChoicePoint Precision Marketing
Generalized Additive Model and Applications in Direct Marketing Sandeep Kharidhi and WenSui Liu ChoicePoint Precision Marketing Abstract Logistic regression 1 has been widely used in direct marketing applications
More informationUX Research in the Product Lifecycle
UX Research in the Product Lifecycle I incorporate how users work into the product early, frequently and iteratively throughout the development lifecycle. This means selecting from a suite of methods and
More informationResPubliQA 2010
SZTAKI @ ResPubliQA 2010 David Mark Nemeskey Computer and Automation Research Institute, Hungarian Academy of Sciences, Budapest, Hungary (SZTAKI) Abstract. This paper summarizes the results of our first
More informationIBM Security AppScan Enterprise v9.0.1 Importing Issues from Third Party Scanners
IBM Security AppScan Enterprise v9.0.1 Importing Issues from Third Party Scanners Anton Barua antonba@ca.ibm.com October 14, 2014 Abstract: To manage the challenge of addressing application security at
More informationIt was a dark and stormy night. Seriously. There was a rain storm in Wisconsin, and the line noise dialing into the Unix machines was bad enough to
1 2 It was a dark and stormy night. Seriously. There was a rain storm in Wisconsin, and the line noise dialing into the Unix machines was bad enough to keep putting garbage characters into the command
More information4. Write a sum-of-products representation of the following circuit. Y = (A + B + C) (A + B + C)
COP 273, Winter 26 Exercises 2 - combinational logic Questions. How many boolean functions can be defined on n input variables? 2. Consider the function: Y = (A B) (A C) B (a) Draw a combinational logic
More informationAgile Accessibility. Presenters: Ensuring accessibility throughout the Agile development process
Agile Accessibility Ensuring accessibility throughout the Agile development process Presenters: Andrew Nielson, CSM, PMP, MPA Ann Marie Davis, CSM, PMP, M. Ed. Cammie Truesdell, M. Ed. Overview What is
More informationCertified Digital Forensics Examiner
Certified Digital Forensics Examiner ACCREDITATIONS EXAM INFORMATION The Certified Digital Forensics Examiner exam is taken online through Mile2 s Assessment and Certification System ( MACS ), which is
More informationPlan for today. CS276B Text Retrieval and Mining Winter Vector spaces and XML. Text-centric XML retrieval. Vector spaces and XML
CS276B Text Retrieval and Mining Winter 2005 Plan for today Vector space approaches to XML retrieval Evaluating text-centric retrieval Lecture 15 Text-centric XML retrieval Documents marked up as XML E.g.,
More informationBuilding an Assurance Foundation for 21 st Century Information Systems and Networks
Building an Assurance Foundation for 21 st Century Information Systems and Networks The Role of IT Security Standards, Metrics, and Assessment Programs Dr. Ron Ross National Information Assurance Partnership
More informationWHITE PAPER ediscovery & Netmail. SEARCH, PRODUCE, and EXPORT EXACTLY WHAT YOU RE LOOKING FOR.
WHITE PAPER ediscovery & Netmail SEARCH, PRODUCE, and EXPORT EXACTLY WHAT YOU RE LOOKING FOR. ediscovery and Netmail In the ediscovery world, the Electronic Discovery Reference Model (EDRM) has been the
More informationQuestion 1: Duplicate Counter (30%)
Question 1: Duplicate Counter (30%) Write a program called Duplicates.java which will determine whether a string contains duplicate characters, and where they occur. Your program should read in a single
More informationInformation Bulletin
Application of Primary and Secondary Reference Documents Version 1.1 Approved for release July 2014 Table of Contents 1.0 Purpose statement... 3 2.0 Audience... 3 3.0 BCA requirements and referenced documents...
More informationLAB: FOR LOOPS IN C++
LAB: FOR LOOPS IN C++ MODULE 2 JEFFREY A. STONE and TRICIA K. CLARK COPYRIGHT 2014 VERSION 4.0 PALMS MODULE 2 LAB: FOR LOOPS IN C++ 2 Introduction This lab will provide students with an introduction to
More informationSlide Set 5. for ENEL 353 Fall Steve Norman, PhD, PEng. Electrical & Computer Engineering Schulich School of Engineering University of Calgary
Slide Set 5 for ENEL 353 Fall 207 Steve Norman, PhD, PEng Electrical & Computer Engineering Schulich School of Engineering University of Calgary Fall Term, 207 SN s ENEL 353 Fall 207 Slide Set 5 slide
More informationRepetition Structures
Repetition Structures Chapter 5 Fall 2016, CSUS Introduction to Repetition Structures Chapter 5.1 1 Introduction to Repetition Structures A repetition structure causes a statement or set of statements
More informationCondition-Controlled Loop. Condition-Controlled Loop. If Statement. Various Forms. Conditional-Controlled Loop. Loop Caution.
Repetition Structures Introduction to Repetition Structures Chapter 5 Spring 2016, CSUS Chapter 5.1 Introduction to Repetition Structures The Problems with Duplicate Code A repetition structure causes
More informationSearching for Expertise
Searching for Expertise Toine Bogers Royal School of Library & Information Science University of Copenhagen IVA/CCC seminar April 24, 2013 Outline Introduction Expertise databases Expertise seeking tasks
More informationNon-Linearity of Scorecard Log-Odds
Non-Linearity of Scorecard Log-Odds Ross McDonald, Keith Smith, Matthew Sturgess, Edward Huang Retail Decision Science, Lloyds Banking Group Edinburgh Credit Scoring Conference 6 th August 9 Lloyds Banking
More informationCS47300: Web Information Search and Management
CS47300: Web Information Search and Management Prof. Chris Clifton 27 August 2018 Material adapted from course created by Dr. Luo Si, now leading Alibaba research group 1 AD-hoc IR: Basic Process Information
More informationSample Exam. Certified Tester Foundation Level
Sample Exam Certified Tester Foundation Level Answer Table ASTQB Created - 2018 American Stware Testing Qualifications Board Copyright Notice This document may be copied in its entirety, or extracts made,
More informationCertified Digital Forensics Examiner
Certified Digital Forensics Examiner Course Title: Certified Digital Forensics Examiner Duration: 5 days Class Format Options: Instructor-led classroom Live Online Training Prerequisites: A minimum of
More informationUse of Synthetic Data in Testing Administrative Records Systems
Use of Synthetic Data in Testing Administrative Records Systems K. Bradley Paxton and Thomas Hager ADI, LLC 200 Canal View Boulevard, Rochester, NY 14623 brad.paxton@adillc.net, tom.hager@adillc.net Executive
More informationXBRL US Domain Steering Committee Taxonomy Review
XBRL US Domain Steering Committee Taxonomy Review for XBRL US Work In Process Taxonomy 2016 As Approved by the DSC on September 8, 2016 Prepared by: Scott Theis, DSC Chairman Campbell Pryde Michelle Savage
More informationInformation Technology Branch Organization of Cyber Security Technical Standard
Information Technology Branch Organization of Cyber Security Technical Standard Information Management, Administrative Directive A1461 Cyber Security Technical Standard # 1 November 20, 2014 Approved:
More informationMultimedia Information Retrieval
Multimedia Information Retrieval Prof Stefan Rüger Multimedia and Information Systems Knowledge Media Institute The Open University http://kmi.open.ac.uk/mmis Multimedia Information Retrieval 1. What are
More informationViewpoint Review & Analytics
The Viewpoint all-in-one e-discovery platform enables law firms, corporations and service providers to manage every phase of the e-discovery lifecycle with the power of a single product. The Viewpoint
More informationCertification Standing Committee (CSC) Charter. Appendix A Certification Standing Committee (CSC) Charter
Appendix A A1 Introduction A1.1 CSC Vision and Mission and Objectives Alignment with Boundaryless Information Flow: Our vision is a foundation of a scalable high integrity TOGAF certification programs
More informationCS6375: Machine Learning Gautam Kunapuli. Mid-Term Review
Gautam Kunapuli Machine Learning Data is identically and independently distributed Goal is to learn a function that maps to Data is generated using an unknown function Learn a hypothesis that minimizes
More informationOCM ACADEMIC SERVICES PROJECT INITIATION DOCUMENT. Project Title: Online Coursework Management
OCM-12-025 ACADEMIC SERVICES PROJECT INITIATION DOCUMENT Project Title: Online Coursework Management Change Record Date Author Version Change Reference March 2012 Sue Milward v1 Initial draft April 2012
More informationNYS Early Learning Trainer Credential. Portfolio Instructions
TC Portfolio Guidelines 8/17/2011 Contents Trainer Definitions 3 General Instructions.....4 Credential Levels...4 Portfolio Structure...5 Portfolio Content Parts 1 and 2: Portfolio Entries.........5 Portfolio
More informationChapter 4 EDGE Approval Protocol for Auditors Version 3.0 June 2017
Chapter 4 EDGE Approval Protocol for Auditors Version 3.0 June 2017 Copyright 2017 International Finance Corporation. All rights reserved. The material in this publication is copyrighted by International
More informationEXAM PREPARATION GUIDE
When Recognition Matters EXAM PREPARATION GUIDE PECB Certified ISO 22000 Lead Auditor www.pecb.com The objective of the Certified ISO 22000 Lead Auditor examination is to ensure that the candidate has
More informationKuratowski Notes , Fall 2005, Prof. Peter Shor Revised Fall 2007
Kuratowski Notes 8.30, Fall 005, Prof. Peter Shor Revised Fall 007 Unfortunately, the OCW notes on Kuratowski s theorem seem to have several things substantially wrong with the proof, and the notes from
More informationGraphical Models. David M. Blei Columbia University. September 17, 2014
Graphical Models David M. Blei Columbia University September 17, 2014 These lecture notes follow the ideas in Chapter 2 of An Introduction to Probabilistic Graphical Models by Michael Jordan. In addition,
More informationToday s Topics. Percentile ranks and percentiles. Standardized scores. Using standardized scores to estimate percentiles
Today s Topics Percentile ranks and percentiles Standardized scores Using standardized scores to estimate percentiles Using µ and σ x to learn about percentiles Percentiles, standardized scores, and the
More informationConfiguring IP Multicast Routing
34 CHAPTER This chapter describes how to configure IP multicast routing on the Cisco ME 3400 Ethernet Access switch. IP multicasting is a more efficient way to use network resources, especially for bandwidth-intensive
More informationIntroduction to Counting, Some Basic Principles
Introduction to Counting, Some Basic Principles These are the class notes for week. Before we begin, let me just say something about the structure of the class notes. I wrote up all of these class notes
More informationInstructions for Form DS-7787: Disclosure of Violations of the Arms Export Control Act
Instructions for Form DS-7787: Disclosure of Violations of the Arms Export Control Act General Instructions: 1 The size of the text field will correspond to the type of information required, with more
More informationLinear combinations of simple classifiers for the PASCAL challenge
Linear combinations of simple classifiers for the PASCAL challenge Nik A. Melchior and David Lee 16 721 Advanced Perception The Robotics Institute Carnegie Mellon University Email: melchior@cmu.edu, dlee1@andrew.cmu.edu
More informationHMH Leadership Form (Leader Guide)
b a a b c Overview: Leadership Evaluation Form Getting Started: On the Home Page, you ll see a To-Do tile for any modules that have pending tasks assigned to you. Either (a) Click on the hyperlink to navigate
More informationWHITEPAPER THE EVOLUTION OF APPSEC: FROM WAFS TO AUTONOMOUS APPLICATION PROTECTION
WHITEPAPER THE EVOLUTION OF APPSEC: FROM WAFS TO AUTONOMOUS APPLICATION PROTECTION 2 Web application firewalls (WAFs) entered the security market at the turn of the century as web apps became increasingly
More informationSample Exam. Advanced Test Automation - Engineer
Sample Exam Advanced Test Automation - Engineer Questions ASTQB Created - 2018 American Software Testing Qualifications Board Copyright Notice This document may be copied in its entirety, or extracts made,
More informationData Center Consolidation and Migration Made Simpler with Visibility
Data Center Consolidation and Migration Made Simpler with Visibility Abstract The ExtraHop platform takes the guesswork out of data center consolidation and migration efforts by providing complete visibility
More informationThe HIPAA Omnibus Rule
The HIPAA Omnibus Rule What You Should Know and Do as Enforcement Begins Rebecca Fayed, Associate General Counsel and Privacy Officer Eric Banks, Information Security Officer 3 Biographies Rebecca C. Fayed
More informationWECC Internal Controls Evaluation Process WECC Compliance Oversight Effective date: October 15, 2017
WECC Internal Controls Evaluation Process WECC Compliance Oversight Effective date: October 15, 2017 155 North 400 West, Suite 200 Salt Lake City, Utah 84103-1114 WECC Internal Controls Evaluation Process
More information